This study evaluates 17 leading LLMs on their ability to follow multiple information threads through near-million-token contexts, revealing performance degradation but strong thread safety.

Jonathan Roberts, Kai Han, Samuel Albanie

SimpleQA benchmark evaluates language models on short factual questions, challenging and easy to grade.

Jason Wei, Nguyen Karina, Hyung Won Chung et al.

MM-Embed leverages multimodal large models for universal retrieval, surpassing SOTA with 52.7% R@5 on M-BEIR.

Sheng-Chieh Lin, Chankyu Lee, Mohammad Shoeybi et al.

CRMArena benchmarks LLMs on nine realistic CRM tasks using Salesforce-based data; top models achieve less than 58% success, highlighting room for improvement.

Kung-Hsiang Huang, Akshara Prabhakar, Sidharth Dhawan et al.

Hunyuan-Large is Tencent's open-source MoE model with 52 billion activated parameters, handling up to 256K tokens.

Xingwu Sun, Yanfeng Chen, Yiqing Huang et al.

Defines SLM by task capability and resource limits; analyzes techniques, applications, and future directions.

Fali Wang, Zhiwei Zhang, Xianren Zhang et al.

This study enhances offline RL agents using diverse, informative language feedback, achieving over 10% performance gains on benchmarks.

Jiajun Xi, Yinong He, Jianing Yang et al.

Survey of cultural awareness data collection and benchmarking methods in multimodal LLMs, emphasizing cross-cultural datasets and evaluation metrics.

Siddhesh Pawar, Junyeong Park, Jiho Jin et al.

Energy-based diffusion language model (EDLM) leverages residual energy models to improve text generation, outperforming existing diffusion models and approaching autoregressive perplexity.

Minkai Xu, Tomas Geffner, Karsten Kreis et al.

Constructed M2RC-EVAL, a multilingual repository-level code completion benchmark with AST-based fine-grained annotations for 18 languages.

Jiaheng Liu, Ken Deng, Congnan Liu et al.

CycleResearcher employs reinforcement learning to automate research from literature review to peer review, reducing prediction MAE by 26.89%.

Yixuan Weng, Minjun Zhu, Guangsheng Bao et al.

Proposed Relaxed Recursive Transformers with layer-wise LoRA for effective parameter sharing, achieving near-full model performance.

Sangmin Bae, Adam Fisch, Hrayr Harutyunyan et al.

MAPO integrates momentum into natural language gradient descent, reducing convergence time by 77.9% and boosting peak F1 score by 5.28%.

Anthony Cui, Pranav Nandyalam, Andrew Rufail et al.

Proposes similarity-adjusted surprisal, leveraging Ricotta and Szeidl’s diversity index, to enhance reading time prediction beyond standard surprisal.

Clara Meister, Mario Giulianelli, Tiago Pimentel

ReflecTool framework enhances clinical agents' tool usage in the medical domain, outperforming pure LLMs by over 10 points in experiments.

Yusheng Liao, Shuyang Jiang, Yanfeng Wang et al.

VoiceBench benchmark evaluates LLM-based voice assistants across diverse real-world scenarios, revealing performance gaps in robustness and safety, with detailed multi-metric analysis.

Yiming Chen, Xianghu Yue, Chen Zhang et al.

Interchangeable Token Embeddings combine shared semantics with random identity, reaching 95.94% LTL correctness and extending vocabularies.

İlker Işık, Ramazan Gokberk Cinbis, Ebru Aydin Gol

Proposed API-calling and Hybrid Agents, API Agent improved by 24.0% on WebArena, achieving 38.9% success rate.

Yueqi Song, Frank Xu, Shuyan Zhou et al.

Using ALTI, this study analyzes layer-wise token contributions in LLM-based MT, revealing source dominance and positional biases.

Emmanouil Zaranis, Nuno M. Guerreiro, André F. T. Martins

Proposed TMCHT task and ARCJ method achieve 52.93% attack success in multi-agent systems.

Tianyi Men, Pengfei Cao, Zhuoran Jin et al.